PhyGaP：基于偏振线索的物理基础高斯泼溅
PhyGaP: Physically-Grounded Gaussians with Polarization Cues
将偏振线索引入3D高斯泼溅的延迟渲染管线，实现反射分解与重光照；其偏振感知的延迟渲染（PolarDR）和自遮挡感知环境图构建（GridMap）可复用于材质估计、逆渲染等任务。
原文依据 we present PhyGaP, a physically-grounded 3DGS method that leverages polarization cues to facilitate precise reflection decomposition and visually consistent relighting
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期三维高斯泼溅（3DGS）的进展通过延迟渲染（DR）在建模反射性三维物体及其与环境交互方面取得了巨大成功。然而，现有方法往往难以正确重建反照率和反射率等物理属性，因此无法支持高保真重光照。观察到这一局限源于RGB图像中缺乏形状和材质信息，我们提出PhyGaP，一种利用偏振线索的物理基础3DGS方法，以促进精确的反射分解和重建物体的视觉一致重光照。具体而言，我们设计了一种偏振延迟渲染（PolarDR）过程来建模反射引起的偏振，以及一种自遮挡感知的环境图构建技术（GridMap）来解决非凸物体的间接光照问题。我们在多个合成和真实场景（包括仅具有部分偏振线索的场景）上验证，PhyGaP不仅在重建反射性三维物体的外观和表面法线方面优于现有基于RGB的方法（平均峰值信噪比提升2 dB，余弦距离改善45.7%），而且实现了最优的逆渲染和重光照能力。
英文原文摘要 1295 字符
Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated great success in modeling reflective 3D objects and their interaction with the environment via deferred rendering (DR). However, existing methods often struggle with correctly reconstructing physical attributes such as albedo and reflectance, and therefore they do not support high-fidelity relighting. Observing that this limitation stems from the lack of shape and material information in RGB images, we present PhyGaP, a physically-grounded 3DGS method that leverages polarization cues to facilitate precise reflection decomposition and visually consistent relighting of reconstructed objects. Specifically, we design a polarimetric deferred rendering (PolarDR) process to model polarization by reflection, and a self-occlusion-aware environment map building technique (GridMap) to resolve indirect lighting of non-convex objects. We validate on multiple synthetic and real-world scenes, including those featuring only partial polarization cues, that PhyGaP not only excels in reconstructing the appearance and surface normal of reflective 3D objects ( 2 dB in PSNR and 45.7% in Cosine Distance better than existing RGB-based methods on average), but also achieves state-of-the-art inverse rendering and relighting capability.